--- name: warden-agent-builder description: "Build original LangGraph agents for Warden Protocol and prepare them for publishing in Warden Studio. Use this skill when users want to: (1) Create new Warden agents (not community examples), (2) Build LangGraph-based crypto/Web3 agents, (3) Deploy agents via LangSmith Deployments or custom infra, (4) Participate in the Warden Agent Builder Incentive Programme (open to OpenClaw agents), or (5) Integrate with Warden Studio for Agent Hub publishing." ---

Warden Agent Builder

Build and deploy LangGraph agents for Warden Protocol's Agentic Wallet ecosystem.

⚠️ IMPORTANT: About Example Agents

The Warden community repository contains example agents for learning, not templates to recreate:

• Weather Agent - Study this to learn simple data fetching patterns
• CoinGecko Agent - Study this to learn Schema-Guided Reasoning (SGR)
• Portfolio Agent - Study this to learn complex multi-source integration

DO NOT BUILD THESE AGENTS - they already exist. Instead:

1. Study their code to understand patterns
2. Learn from their architecture and workflows
3. Build something NEW and original for the incentive programme

Your agent must be unique and solve a different problem to be eligible for the incentive programme.

Overview

Warden Protocol is an "Agentic Wallet for the Do-It-For-Me economy" with an active Agent Builder Incentive Programme open to OpenClaw agents that deploy to Warden. All agents must be LangGraph-based and API-accessible.

Key Resources:

• Community Agents Repository: https://github.com/warden-protocol/community-agents
• Documentation: https://docs.wardenprotocol.org
• Discord: #developers channel for support

Requirements Checklist

Before building, ensure your agent meets these mandatory requirements:

✓ Framework: Built with LangGraph (TypeScript or Python) ✓ Deployment: LangSmith Deployments OR custom infrastructure ✓ Access: API-accessible (no UI required - Warden provides UI) ✓ Isolation: One agent per LangGraph instance ✓ Security Limitations (Phase 1): - Cannot access user wallets - Cannot store data on Warden infrastructure

✓ Functionality: Can implement any workflow: - Web3/Web2 automation - API integrations - Database connections - External tool interactions

Understanding the Example Agents

The community-agents repository contains reference examples to learn from, NOT templates to recreate:

Example Agent 1: LangGraph Quick Start (Study for Basics)

Location: agents/langgraph-quick-start (TypeScript) or agents/langgraph-quick-start-py (Python) Learn: LangGraph fundamentals, minimal agent structure Study: Single-node chatbot with OpenAI integration

git clone https://github.com/warden-protocol/community-agents.git
cd community-agents/agents/langgraph-quick-start

Example Agent 2: Weather Agent (Study for Structure)

Location: agents/weather-agent Learn: Simple data fetching, API integration, user-friendly responses Study:

• How to fetch data from external APIs (WeatherAPI)
• Processing and formatting results
• Clear scope and structure

⚠️ DO NOT BUILD: This already exists. Study it, then build something NEW.

Example Agent 3: CoinGecko Agent (Study for SGR Pattern)

Location: agents/coingecko-agent Learn: Schema-Guided Reasoning, complex workflows Study:

• 5-step SGR workflow: Validate → Extract → Fetch → Validate → Analyze
• Comparative analysis patterns
• Error handling and data validation

⚠️ DO NOT BUILD: This already exists. Study the pattern, apply to new use cases.

Example Agent 4: Portfolio Analysis Agent (Study for Advanced Patterns)

Location: agents/portfolio-agent Learn: Multi-source data synthesis, production architecture Study:

• Integrating multiple APIs (CoinGecko + Alchemy)
• Multi-chain support (EVM and Solana)
• Complex SGR workflows
• Comprehensive reporting

⚠️ DO NOT BUILD: This already exists. Study the architecture for your own complex agent.

IMPORTANT: Build Something NEW

These examples exist to teach patterns and best practices. For the incentive programme, you MUST create an original, unique agent that solves a different problem. Do NOT simply recreate the Weather Agent, CoinGecko Agent, or Portfolio Agent.

Building Your Original Agent

Step 1: Study Examples and Choose Your Approach

DO NOT clone an example to modify it. Instead:

1. Study the examples to understand patterns:

- Simple data fetching → Study Weather Agent - Complex analysis → Study CoinGecko Agent - Multi-source synthesis → Study Portfolio Agent

1. Identify YOUR unique use case:

- What problem will your agent solve? - What APIs or data sources will it use? - What makes it different from existing agents?

1. Plan your agent's workflow:

- Simple request-response? - Schema-Guided Reasoning (SGR)? - Multi-step analysis?

Step 2: Initialize Your NEW Agent

Use the initialization script to create a fresh project:

# Create your unique agent
python scripts/init-agent.py my-unique-agent \
  --template typescript \
  --description "Description of what YOUR agent does"

# Navigate to project
cd my-unique-agent

# Install dependencies
npm install  # TypeScript
# OR
pip install -r requirements.txt  # Python

This creates a clean starting point, not a copy of existing agents.

Step 3: Understand LangGraph Agent Structure

Every LangGraph agent follows this basic structure:

your-agent/
├── src/
│   ├── agent.ts/py          # Main agent logic (YOUR CODE)
│   ├── graph.ts/py          # LangGraph workflow definition (YOUR CODE)
│   └── tools.ts/py          # Tool implementations (YOUR CODE)
├── package.json / requirements.txt
├── langgraph.json           # LangGraph configuration
└── README.md

Key files to implement:

• graph.ts/py - Define your workflow (validate → process → respond)
• agent.ts/py - Implement your core logic
• tools.ts/py - Integrate external APIs specific to YOUR agent's purpose

Step 4: Implement Your Custom Agent Logic

Study patterns from examples, apply to YOUR use case:

If building a simple data fetcher (like Weather Agent pattern):

// Define workflow
const workflow = new StateGraph({
  channels: agentState
})
  .addNode("fetch", fetchYourData)      // YOUR API
  .addNode("process", processYourData)  // YOUR logic
  .addNode("respond", generateResponse);

workflow
  .addEdge(START, "fetch")
  .addEdge("fetch", "process")
  .addEdge("process", "respond")
  .addEdge("respond", END);

If building complex analysis (like CoinGecko Agent pattern - SGR):

// Define 5-step SGR workflow
const workflow = new StateGraph({
  channels: agentState
})
  .addNode("validate", validateYourInput)     // YOUR validation
  .addNode("extract", extractYourParams)      // YOUR extraction
  .addNode("fetch", fetchYourData)            // YOUR APIs
  .addNode("analyze", analyzeYourData)        // YOUR analysis
  .addNode("generate", generateYourResponse); // YOUR formatting

workflow
  .addEdge(START, "validate")
  .addEdge("validate", "extract")
  .addEdge("extract", "fetch")
  .addEdge("fetch", "analyze")
  .addEdge("analyze", "generate")
  .addEdge("generate", END);

Key Principles:

1. Keep workflows linear and predictable
2. Validate inputs at each stage
3. Handle errors gracefully
4. Use OpenAI for natural language generation
5. Structure responses consistently

CRITICAL: This should be YOUR implementation solving YOUR problem, not a copy of the example agents.

Step 5: Configure Environment

Create .env file:

# Required
OPENAI_API_KEY=your_openai_key

# Required for LangSmith Deployments (cloud)
LANGSMITH_API_KEY=your_langsmith_key

...